知识卡片
角向差分恢复累积光贡献
在本章近似中,地面测量随角度累积来自隐藏场景的光;比较相邻扇形区域,就估计新增角区间的贡献。实际以带正负权重的空间掩模汇总像素,利用区域平均增强微弱变化。垂直方向已被积分,恢复结果并不是完整二维人像。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
take a derivative with respect to angle. This makes intuitive sense, as the light intensities on the ground integrate all the light up to the angle of the vertical edge. To find the 1D signal at the angle of the edge, we ask, “What does one pie-shaped ray from the wall see that the pie-shaped ray next to it doesn't see?”
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第07章《作为线性系统的相机》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c007.xhtml)
- 结论依据:摘录中关于角向差分恢复累积光贡献的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:take a derivative with respect to angle. This makes intuitive sense, as the light intensities on the ground integrate all the light up to the angle of the vertical edge. To find the 1D signal at the angle of the edge, we ask, “What does one pie-shaped ray from the wall see that the pie-shaped ray next to it doesn't see?”